© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126010
    Prev
    Next
    INDEX
    Explanations

    website domain references, particularly focusing on those ending in '.com'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.07
    rof
    -0.07
    bum
    -0.06
    EMA
    -0.06
    weise
    -0.06
     medio
    -0.06
    lich
    -0.06
    utr
    -0.06
     suppress
    -0.05
     prop
    -0.05
    POSITIVE LOGITS
    owns
    0.08
    .au
    0.08
     Fav
    0.08
    abcdefghijklmnop
    0.08
    'gc
    0.07
    ownik
    0.07
    _RCC
    0.07
    اÛĮاÙĨ
    0.07
    огÑĥ
    0.07
    rowse
    0.07
    Activations Density 0.033%

    No Known Activations